Gradient descent relies on trial and error to optimize an algorithm, aiming for minima in a 3D landscape.
Credit: Alexander Amini, Daniela Rus, Massachusetts Institute of Technology, adapted by M. Atarod/Science
Ali Rahimi, a researcher in artificial intelligence (AI) at Google in San Francisco, California, took a swipe at his field last December—and received a 40-second ovation for it.
From Science Magazine View Full Article
No entries found